Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases indicating purpose or intentionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.59
    UrlResolution
    -0.47
     CascadeType
    -0.47
    cu
    -0.46
    enterOuterAlt
    -0.44
     Codable
    -0.44
    Hochspringen
    -0.42
    JKLM
    -0.41
     LoggerFactory
    -0.41
    AppMethodBeat
    -0.41
    POSITIVE LOGITS
    exprimer
    0.50
     burada
    0.46
    tagHelperRunner
    0.46
     kaybet
    0.45
     насељу
    0.45
    OOTDTY
    0.42
     fizer
    0.41
     tartalomajánló
    0.40
    ViewFeatures
    0.39
     marinho
    0.39
    Act Density 1.188%

    No Known Activations